🐻 Gumini 1B Base i1 GGUF (구미니) Built with Qwen Model Description GGUF quantized versions of GuminiResearch/Gumini 1B Base for use with llama.cpp and compatible tools (Ollama, LM Studio, etc.). All quantizations were created using importance matrix (imatrix) calibration for optimal quality preservation. This is a BASE model , not instruction tuned. It produces text continuations rather than conversational responses. Model Details Attribute Value Original Model Gumini 1B Base Quantized by Gumin Kwon (권구민) Parameters 1.08B Layers 10 Hidden Size 2048 Base PPL (F16) 15.36 Quantization Results Perplexity Comparison PPL vs Size Trade off Recommended Quantizations Quant PPL Size PPL Δ Quality Use Case Q8 0 15.40 1.1G +0.03 Excellent Maximum quality Q6 K 15.43 852M +0.07 Excellent High quality Q5 K M 15.46 769M +0.10 Excellent Balanced (recommended) Q4 K M 15.61 691M +0.25 Very Good Size optimized IQ4 XS 15.69 641M +0.33 Very Good imatrix 4 bit IQ3 M 16.17 574M +0.81 Good Mobile/Edge All Quantization Results Usage With llama.cpp With Ollama With LM Studio 1. Download any .gguf file from this repo 2. Import into LM Studio 3. Start generating! Quantization Guide Tips Best quality : Use Q8 0…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy